# Testing Methodology

For the longest time, maternity leave has been criticized as a factor that reduces women’s participation in a given economy. Additionally, this factor is reported to lead to women pushing their up their chance to be mothers so as to remain in their careers for long. Such statements merit empirical research. In this paper, empirical research has been done. The empirical analysis follows the regression method. Regression can either be logistical or linear. In this case, linear regression is used. Linear regression utilizes a regression line whereby data is sampled and measured how far it is distributed along the regression line. Thus, the model takes the form of a linear equation.

The benefits of using linear regression are that multiple dependent variables and independent variables can be measured against each other. Unlike other methods such as correlation analysis, it is possible to make sure that compare the data between two variables at the same time. In this case, there are two main variables. These are the dependent variable (Y), which is women’s labour force participation. The other variable is the independent variable (X), which, in this case, is the fertility rate. Thus, the linear regression model selected was used to measure the relationship between fertility rate and labour force participation. It is assumed that the two of them have a linear relationship. Given that the data collected is of the time-series model, it means that there is a linear relationship between the two. This is because the data has a time aspect whereby it accumulates over time. Thus, it is essential to use the regression model based on the regression line.

The other merit of using the regression model is that it shows the significance and strength of the independent and dependent variables altogether. This is essential in this paper as the idea is to assess the significance and strength of the impact that fertility rates have on women’s labour force participation. The error term and the intercept are both accounted for in the linear equation. In this way, the regression model will allow the study to compute the relationship between the two variables in an accurate manner.

# Empirical Model

The empirical model used has the predictor variable, the error term, and the intercept. The coefficient of determination for the predictor variables will be revealed in this study. The equation was as shown below.

¥ = β + β1F + u

Where              ¥ represented women’s labour force participation

β represented the intercept or constant in the equation

β1 represented the coefficients of determinant

F represented the Fertility Rate

u represented the error term in the equation

The equation of the empirical model, as shown above, made it possible for the researcher to identify the effect of the coefficient of determination as well as the error term. The error term helps to find the difference between what is expected and what is the actual state of things. In this way, the different manifestations of the data that may emerge during the analysis were catered for by the error term.

# Data

In this case, secondary data was sourced to try and explain the impact of Canada’s fertility rate on women’s labour force participation. The rationale of using secondary data is to make it possible to cover a wide historical period without having to engage in lengthy data collection procedures. This is because the study chose to engage in time series data that spreads over more than five years. This means collecting data on the variable investigated based on many years. The outliers in such data are visible, making it easier to pull them out. The study used fertility rates obtained based on Canadian women aged between 25 and 34 years. This was the preferred cohort for measurement due to the high fertility rates of such women in normal standards. The labour participation rate data were obtained based on Canada’s reported historical figures

# Hypothesized Results

The study expects that the hypothesized results of the study to be a negative coefficient of determination when it comes to the X value. This means that women’s labour force participation will increase as much as fertility rates decline in Canada. This is expected because as the fertility rate decreases, women have fewer children and hence fewer household responsibilities. In this way, women are able to venture into labour force participation. This is because they can access jo opportunities that require them to travel far from home or stay in the workplace for long hours. As such, the fertility rate increase will limit the participation of women in labour because most of them will have families limiting their movements and flexibility. Thus, it is expected that an increase in the fertility rate will lead to a decrease in women’s labour force participation.

# Actual Results

The actual results reported after the analysis are reported here. The model summary shown in table 1 has the R-value, the R square, the adjusted R square and the standard error of the estimate. These elements are used to measure the validity of the data used and the aptness of the regression model to the data. Additionally, the assumptions that were outlined at the beginning of this report that support regression analysis are tested too.

Table 1: Regression Model Summary

 Model R R Squared Adjusted R Squared Std. Error of the Estimate 1 -0.976 0.953 0.983 2.711

The R-value measures the variance that the independent variables have against the dependent variable. In this case, the R-value is negative, which means that the net effect of the predictor variable is negative. However, the proportion of the variance that the predictor variable can explain when it comes to the criterion variable is still high at 97.6%. The R squared test is used to measure how well the current predictor variable can predict the variances in the criterion variable. In other words, it is used to tell of the independent variables have adequate prediction capabilities towards the dependent variable. Therefore, the results of the study show that the R square stands at 0.953. This means that the proportion that the independent variable can explain the dependent variable is 95.3%. Moreover, the adjusted R square value is used to measure the relevance of the independent variables of this study. The adjusted R squared value in this study was found to be 0.983, which means that 98.3% of the outcomes regarding the dependent variable is explained by the independent variable. Thus, it is important that additional studies are done with other different variables to cover the remaining 1.7%.

In table 2, the ANOVA test results are presented. The ANOVA test helps in determining the results on whether to accept or reject the null hypothesis. The null hypothesis, in this case, was that fertility rates do not impact women’s labour force participation in any way. The alternative hypothesis is that the fertility rate in women affects women’s labour force participation.

Table 2: ANOVA Results

 Model Sum of Squares df Mean Square F Sig. 1 Regression 7822.522 1 7822.522 1064.512 0.000 Residual 382.12 52 7.348 Total 8204.642 53 a. Dependent Variable: Women’s labour force participation

From table 2, the F value and the overall significance of the model were revealed. The F test was done to identify how far the data was scattered between two means. If the F value gives a large figure, this means that there is great dispersion in the data. Arkes (2019) reported that so long as the F value is larger than the p-value (which in this case was 0.031), then the data used can be deduced to have optimal dispersion that will answer be used in rejecting or approving the hypotheses.

The overall significance of the model was found to be 0.000, which is also high compared to the p-value. When the significance is less than the p-value, it means that the data used has the variance levels and evidence to make the desired predictions in the model. In this case, the significance level was lower than the p-value, which means variance and data dispersion to the mean were optimal (Çankaya 2019, 1166-1172).

In table 3, the coefficient of determination was presented. These coefficients were reported based on the analysis that was done with the p-value held at 0.031 and the F value reported to be 1064.512. This means that the level of accuracy of the coefficient of determination as measured by the p-value and the F value was high.

Table 3: Coefficients of Determination

 Model Unstandardized Coefficients Standardized Coefficients t Sig. B Std. Error Beta 1 (Constant) 1.896 0.373 5.083 0.000 Fertility Rate -0.803 0.275 -0.256 2.920 0.005
1. Dependent Variable: Women’s labour force participation

As per the results, the coefficient of determination of the independent variable (fertility rate) value was found to be negative. The constant was held at 1.896, with the significance being 0.000. This means that the measure of the coefficient of determination was highly significant and accurate. The results show that an increase in fertility rates in Canada in the period surveyed led to a reduction in labour force participation. Additionally, the study found a unit increase in fertility rates in Canada led to a decline in women’s labour force participation by 0.803 units. This result was found to be significant at 0.005. Thus, fertility rates were found to affect in a negative and significant manner the rate of participation in labour by Canadian women.

# Interpretation of the Results

The study had earlier predicted that there would be a negative coefficient of determination when it comes to the X value. This result was affirmed after the analysis whereby women’s labour force participation increased as much as fertility rates declined in Canada. This was expected because as the fertility rate decreases, women have fewer children and hence fewer household responsibilities. In this way, women were able to venture into labour force participation. This was because they can access job opportunities that require them to travel far from home or stay in the workplace for long hours. As such, the fertility rate increase limited the participation of women in labour because most of them will have families limiting their movements and flexibility. Thus, it has been established that an increase in the fertility rate leads to a decrease in women’s labour force participation in Canada.

# Conclusion

In conclusion, the study found that the relationship between fertility rates and the rate of women’s participation in labour is negative and significant. The results show that an increase in fertility rates in Canada in the period surveyed led to a reduction in labour force participation. Additionally, the study found a unit increase in fertility rates in Canada led to a decline in women’s labour force participation. The study could have been improved by using another variable to cover the variance that was not explained by the single independent variable. Other factors such as health and education attainment should also be studied to help bolster the understanding and insights in the field of labour participation in Canada.