Please use the \"WOMEN13\" data attached to answer the questions below. Data inc
ID: 3296460 • Letter: P
Question
Please use the "WOMEN13" data attached to answer the questions below. Data include the following variables: D = 1 if a woman is looking for a job, 0 otherwise M = 1 if a woman is married, 0 otherwise S = Number of years of schooling for each woman included in the analysis
1) First estimate a linear probability model (LPM) that regresses whether a woman is looking for a job (D) on whether she is married (M) and years of schooling (S). Are the results as expected? Interpret the results with emphasis on a) whether coefficients are statistically significant, b) marginal effects, and c) model fit.
2) Next, estimate a "probit" model using the same data. Are the results as expected? Interpret the results with emphasis on a) whether coefficients are statistically significant, b) marginal effects, and c) model fit.
3) Finally, estimate a "logit" model using the same data. Are the results as expected? Interpret the results with emphasis on a) whether coefficients are statistically significant, b) marginal effects, c) odds ratios, and d) model fit.
OBS A AD D DHAT M S 1 31 0 1 1.2 0 16 2 34 0 1 0.63 1 14 3 41 0 1 0.82 1 16 4 67 1 0 0.55 0 9 5 25 0 1 0.83 0 12 6 58 0 0 0.45 1 12 7 45 0 1 1.01 0 14 8 55 0 1 0.64 0 10 9 43 0 0 0.83 0 12 10 55 0 1 0.45 0 8 11 25 0 1 0.73 0 11 12 41 0 1 1.01 0 14 13 62 0 0 0.45 1 12 14 51 0 1 0.54 1 13 15 39 0 0 0.17 1 9 16 35 0 1 0.64 0 10 17 40 0 1 0.63 1 14 18 43 0 0 0.26 1 10 19 37 0 0 0.45 1 12 20 27 0 1 0.92 0 13 21 28 0 1 1.01 0 14 22 48 0 1 0.45 1 12 23 66 1 0 -0.01 1 7 24 44 0 0 0.35 1 11 25 21 0 0 0.45 1 12 26 40 0 1 0.26 1 10 27 41 0 1 1.11 0 15 28 23 0 0 0.26 1 10 29 31 0 0 0.35 1 11 30 44 0 1 0.45 1 12Explanation / Answer
Here the person is defined as a labour if she has job or actively looking for a job. This cross sectional study of women labour force can be represented by the dummy dependent variables.
Di = 1, if the women is looking for a job or have a job
0, otherwise
It is given that two most important relevant independent variables here are marital status and years of schooling, which can be represented as follows :-
D = f (Mi, Si )
The linear probability model for the same can be interpreted as
Di = 0 + 1 Mi +2 Si + £i
Where £i is error term with variance Pi (1- Pi ).If we estimate the data we obtain standard error in parantheses
The results interpret that both the independent variables have estimated coefficients that are significant in the expected direction. Also 0.32 is quite high for a linear probability model.